Triple

T17611100
Position Surface form Disambiguated ID Type / Status
Subject Swiss Federal Archives E428966 entity
Predicate abbreviation P43 FINISHED
Object SFA
SFA is the abbreviation for the Swiss Federal Archives, the national institution responsible for preserving and providing access to the official records of the Swiss Confederation.
 E1277641 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: SFA | Statement: [Swiss Federal Archives, abbreviation, SFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SFA
Context triple: [Swiss Federal Archives, abbreviation, SFA]
  • A. SFA
    The SFA is the Scottish Football Association, the main governing body for football in Scotland.
  • B. SFA
    SFA is the IATA airport code for Sfax–Thyna International Airport serving the city of Sfax in Tunisia.
  • C. SFA
    SFA is a public university in Nacogdoches, Texas, known for its academic programs, research, and Lumberjacks athletic teams.
  • D. SFA
    SFA is the National Rail station code for Stratford International railway station in London, England.
  • E. SFA State
    SFA State is a public university located in Nacogdoches, Texas, known for its programs in education, forestry, and the liberal arts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SFA
Triple: [Swiss Federal Archives, abbreviation, SFA]
Generated description
SFA is the abbreviation for the Swiss Federal Archives, the national institution responsible for preserving and providing access to the official records of the Swiss Confederation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SFA
Target entity description: SFA is the abbreviation for the Swiss Federal Archives, the national institution responsible for preserving and providing access to the official records of the Swiss Confederation.
  • A. SFA
    The SFA is the Scottish Football Association, the main governing body for football in Scotland.
  • B. SFA
    SFA is the IATA airport code for Sfax–Thyna International Airport serving the city of Sfax in Tunisia.
  • C. SFA
    SFA is a public university in Nacogdoches, Texas, known for its academic programs, research, and Lumberjacks athletic teams.
  • D. SFA
    SFA is the National Rail station code for Stratford International railway station in London, England.
  • E. SFA State
    SFA State is a public university located in Nacogdoches, Texas, known for its programs in education, forestry, and the liberal arts.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46d2d294881908380b2ab0b4d2503 completed April 19, 2026, 5:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01e8241cb481909ebb91e24c6eaf63 completed May 11, 2026, 2:31 p.m.
NEDg Description generation batch_6a01ee1a291c81909fa432ccc787028f completed May 11, 2026, 2:56 p.m.
NED2 Entity disambiguation (via description) batch_6a01eec7e00c81908d88be9f88e924c8 completed May 11, 2026, 2:59 p.m.
Created at: April 10, 2026, 5:51 a.m.